Knowledge catalogue
arXiv:2604.03236v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based educational assistants often provide direct answers offering little incentive for students to explore or enga
arXiv:2608.12037v1 Announce Type: new Abstract: Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust
arXiv:2608.12279v1 Announce Type: new Abstract: Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TT
arXiv:2608.11873v1 Announce Type: new Abstract: In this work, we extend the Dependent Click Model (DCM) Bandits to a multiplayer information-asymmetric setting, where multiple agents interact with a s
arXiv:2608.11576v1 Announce Type: cross Abstract: Video-to-music generation has drawn growing interest for its role in conveying the emotion of visual media, including film. Progress in the field, how
arXiv:2608.11441v1 Announce Type: new Abstract: Low-resource automatic speech recognition (ASR) commonly relies on cross-lingual transfer, where models are adapted from higher-resource donor languages
arXiv:2608.11281v1 Announce Type: cross Abstract: Tool wear prediction is an important task in CNC machining, where accurate monitoring of tool condition supports product quality and process reliabili
arXiv:2608.11727v1 Announce Type: new Abstract: When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference:
arXiv:2608.11499v1 Announce Type: cross Abstract: Task vectors enable model merging without joint retraining. In practice, the subset of task vectors to be merged may vary, but many existing methods u
If you write rules in an AGENTS.md, this one is worth your time. When a coding agent follows your rule, it may have been going to do that anyway. Harness-IF separates the two by scoring 256 rules one
arXiv:2608.11766v1 Announce Type: cross Abstract: Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-leve
arXiv:2602.11650v2 Announce Type: replace Abstract: Although large language models (LLMs) show promise for generating educational feedback, it remains unclear how feedback should be designed (e.g., to
arXiv:2608.11617v1 Announce Type: new Abstract: Ambiguous medical image segmentation aims to provide a series of diverse but plausible segmentation hypotheses. However, existing methods introduce stoc
arXiv:2608.11604v1 Announce Type: new Abstract: Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction
arXiv:2608.11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical ca
arXiv:2608.11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings. This archit
arXiv:2608.12179v1 Announce Type: new Abstract: Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors, trading away cost, power, and inte
arXiv:2608.12253v1 Announce Type: cross Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that
arXiv:2608.12018v1 Announce Type: new Abstract: Regional dialectal variation poses a fundamental challenge to natural language processing (NLP) in Bangla, where over 240 million speakers communicate a
arXiv:2608.11460v1 Announce Type: new Abstract: Large Language Model-powered agents are increasingly used in the workplace via human-artificial intelligence (AI) collaboration. In this new era of work
arXiv:2607.08837v2 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject
arXiv:2608.12123v1 Announce Type: cross Abstract: LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next
arXiv:2608.11587v1 Announce Type: cross Abstract: Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalist
This release brings smaller prompts, longer-running conversations, safer remote access, and more reliable model streaming. External tools and skills are now discovered only when relevant. Long chats g
arXiv:2507.11773v2 Announce Type: replace-cross Abstract: The emergence of breakthrough artificial intelligence (AI) techniques has led to a renewed focus on how small data settings, i.e., settings wi
arXiv:2608.11699v1 Announce Type: new Abstract: Constructing a unified 3D scene understanding model has long been hindered by the topological discrepancies across sensor modalities. While applying the
arXiv:2608.11820v1 Announce Type: new Abstract: Visual data is typically a prerequisite for training existing video anomaly detection (VAD) methods. However, obtaining sufficient annotated anomaly dat
arXiv:2608.11878v1 Announce Type: cross Abstract: Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. Howeve
arXiv:2608.11407v1 Announce Type: new Abstract: Robust traffic simulators are crucial for developing and testing autonomous vehicles to reduce the costly, labor-intensive real-world data collection pr
arXiv:2608.11654v1 Announce Type: new Abstract: Despite the wide deployment of memory in large-model agents, there is no unified formal account of what a memory is or when it is optimal. This paper ta
arXiv:2608.11246v1 Announce Type: new Abstract: The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure
arXiv:2608.11785v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predicti
arXiv:2603.24567v2 Announce Type: replace-cross Abstract: Constrained optimization in high-dimensional black-box settings is difficult due to expensive evaluations, the lack of gradient information, a
arXiv:2608.10245v1 Announce Type: cross Abstract: Inventory and distribution planning in Physical Internet networks requires coordinating factory-hub assignments, factory supply, lateral transshipment
arXiv:2608.10606v1 Announce Type: new Abstract: ASR-roundtrip evaluation is widely used as a scalable proxy for text-to-speech (TTS) intelligibility, but it can produce false negatives for reading err
arXiv:2608.10271v1 Announce Type: cross Abstract: Breast density classification is a critical component of breast cancer risk assessment, yet AI models often struggle to generalize across clinical sit
arXiv:2608.11203v1 Announce Type: new Abstract: This paper presents a self-supervised representation learning framework for understanding 3D skeleton-based human motion in soccer, using future motion
arXiv:2608.10712v1 Announce Type: new Abstract: 3D scene reconstruction, modeling, and rendering are highly relevant for numerous tasks, and 3D Gaussian splatting has become a standard choice in this
arXiv:2608.11200v1 Announce Type: cross Abstract: Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or
arXiv:2608.10441v1 Announce Type: cross Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expen
arXiv:2608.10037v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical groundin
arXiv:2608.10626v1 Announce Type: new Abstract: Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently mul
arXiv:2109.13445v3 Announce Type: replace-cross Abstract: The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the distribution of the training data is not well u
arXiv:2608.11096v1 Announce Type: new Abstract: Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss,
arXiv:2608.10698v1 Announce Type: new Abstract: The rapid development of large language models (LLMs) has increased the need for reliable detection of LLM-generated text, especially in realistic Chine
arXiv:2608.10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), to
arXiv:2608.10843v1 Announce Type: new Abstract: First-order concept synthesis asks a system to infer one formula that classifies labeled objects consistently across several finite relational structure
arXiv:2608.10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept? A common answer repeatedly erases probe directions and reports the stopping
arXiv:2601.10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamic
arXiv:2608.10672v1 Announce Type: cross Abstract: Social interaction has become one of the most common uses of LLMs, yet research on emotional bonds with AI has focused largely on how users experience
arXiv:2608.10170v1 Announce Type: new Abstract: Patient motion remains a source of image degradation in brain MRI, leading to signal loss, blurring, and geometric distortion that compromise quantitati
arXiv:2601.18128v2 Announce Type: replace-cross Abstract: High-dimensional data often exhibit variation that can be captured by lower-dimensional factors. For high-dimensional data from multiple studi
arXiv:2507.06849v3 Announce Type: replace-cross Abstract: Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but ofte
arXiv:2608.09966v1 Announce Type: cross Abstract: European summer warming reflects interactions among background change, persistent ocean--land--circulation states, and same-season variability. We dev
arXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-acce
arXiv:2608.10383v1 Announce Type: new Abstract: Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation. However, most existing studies focus on sequential manipul
arXiv:2509.03140v2 Announce Type: replace-cross Abstract: We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimens
arXiv:2608.11152v1 Announce Type: cross Abstract: Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple dom
arXiv:2608.10277v1 Announce Type: cross Abstract: We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-
arXiv:2608.11044v1 Announce Type: new Abstract: Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing